DICOM MCP Server

DICOM MCP Server for Medical Imaging Systems 🏥

Thedicom-mcpserver enables AI assistants to query, read, and move data on DICOM servers (PACS, VNA, etc.).

--------------------------------------------------------------------- 🧑‍⚕️ User: "Any significant findings in John Doe's previous CT report?" 🧠 LLM → ⚙️ Tools: query_patients → query_studies → query_series → extract_pdf_text_from_dicom 💬 LLM Response: "The report from 2025-03-26 mentions a history of splenomegaly (enlarged spleen)" 🧑‍⚕️ User: "What's the volume of his spleen at the last scan and the scan today?" 🧠 LLM → ⚙️ Tools: (query_studies → query_series → move_series → query_series → extract_pdf_text_from_dicom) x2 (The move_series tool sends the latest CT to a DICOM segmentation node, which returns volume PDF report) 💬 LLM Response: "last year 2024-03-26: 412cm³, today 2025-04-10: 350cm³" ---------------------------------------------------------------------

- 🔍 Query Metadata: Search for patients, studies, series, and instances using various criteria.
- 📄 Read DICOM Reports (PDF): Retrieve DICOM instances containing encapsulated PDFs (e.g., clinical reports) and extract the text content.
- 📥 Download DICOM Files: Download DICOM instances from the server to a local directory using C-GET. Retrieve entire series or specific instances for local analysis and processing.
- ➡️ Send DICOM Images: Send series or studies to other DICOM destinations, e.g. AI endpoints for image segmentation, classification, etc.
- ⚙️ Utilities: Manage connections and understand query options.

# Clone and set up development environment git clone https://github.com/Y5ive9ine/dicom-mcp cd dicom mcp # Create and activate virtual environment uv venv source .venv/bin/activate # Install with test dependencies uv pip install -e ".[dev]"

dicom-mcprequires a YAML configuration file (config.yamlor similar) defining DICOM nodes and calling AE titles. Adapt the configuration or keep as is for compatibility with the sample ORTHANC Server.

nodes: main: host: "localhost" port: 4242 ae_title: "ORTHANC" description: "Local Orthanc DICOM server" current_node: "main" calling_aet: "MCPSCU"

[!WARNING] DICOM-MCP is not meant for clinical use, and should not be connected with live hospital databases or databases with patient-sensitive data. Doing so could lead to both loss of patient data, and leakage of patient data onto the internet. DICOM-MCP can be used with locally hosted open-weight LLMs for complete data privacy.

If you don't have a DICOM server available, you can run a local ORTHANC server using Docker:

Clone the repository and install test dependenciespip install -e ".[dev]

cd tests docker ocmpose up -d cd .. pytest # uploads dummy pdf data to ORTHANC server

Add to your client configuration (e.g.claude_desktop_config.json):

{ "mcpServers": { "dicom": { "command": "uv", "args": ["tool","dicom-mcp", "/path/to/your_config.yaml"] } } }

{ "mcpServers": { "arxiv-mcp-server": { "command": "uv", "args": [ "--directory", "path/to/cloned/dicom-mcp", "run", "dicom-mcp", "/path/to/your_config.yaml" ] } } }

dicom-mcpprovides four categories of tools for interaction with DICOM servers and DICOM data.

- query_patients: Search for patients based on criteria like name, ID, or birth date.
- query_studies: Find studies using patient ID, date, modality, description, accession number, or Study UID.
- query_series: Locate series within a specific study using modality, series number/description, or Series UID.
- query_instances: Find individual instances (images/objects) within a series using instance number or SOP Instance UID

- extract_pdf_text_from_dicom: Retrieve a specific DICOM instance containing an encapsulated PDF and extract its text content.

- retrieve_dicom_instances: Download DICOM instances from the server to a local directory using C-GET. Retrieve entire series or specific instances for local analysis and processing.

- move_series: Send a specific DICOM series to another configured DICOM node using C-MOVE.
- move_study: Send an entire DICOM study to another configured DICOM node using C-MOVE.

- list_dicom_nodes: Show the currently active DICOM node and list all configured nodes.
- switch_dicom_node: Change the active DICOM node for subsequent operations.
- verify_connection: Test the DICOM network connection to the currently active node using C-ECHO.
- get_attribute_presets: List the available levels of detail (minimal, standard, extended) for metadata query results.

The tools can be chained together to answer complex questions:

Tests require a running Orthanc DICOM server. You can use Docker:

# Navigate to the directory containing docker-compose.yml (e.g., tests/) cd tests docker-compose up -d

# From the project root directory pytest

Use the MCP Inspector for debugging the server communication:

npx @modelcontextprotocol/inspector uv run dicom-mcp /path/to/your_config.yaml --transport stdio

- Built usingpynetdicom
- UsesPyPDF2for PDF text extraction

# Find all patients with name starting with "SMITH" patients = query_patients(name_pattern="SMITH*")

# Find CT studies from January 2023 studies = query_studies( modality_in_study="CT", study_date="20230101-20230131" )

# Download entire series to local directory result = retrieve_dicom_instances( series_instance_uid="1.2.840.113619.2.1.1.322.1600364094.412.2005", output_directory="/path/to/local/dicom/files" ) # Download specific instance only result = retrieve_dicom_instances( series_instance_uid="1.2.840.113619.2.1.1.322.1600364094.412.2005", sop_instance_uid="1.2.840.113619.2.1.1.322.1600364094.412.3001", output_directory="/path/to/local/dicom/files" ) print(f"Downloaded {result['total_files']} files ({result['total_size_mb']} MB)") print(f"Files saved to: {result['output_directory']}") # Files will be named with meaningful information like: # "12345_SMITH_20230215_CT_CHEST_AXIAL_Inst001.dcm" # "12345_SMITH_20230215_CT_CHEST_AXIAL_Inst002.dcm"

# Extract text from a DICOM PDF report result = extract_pdf_text_from_dicom( study_instance_uid="1.2.840.113619.2.1.1.322.1600364094.412.1009", series_instance_uid="1.2.840.113619.2.1.1.322.1600364094.412.2005", sop_instance_uid="1.2.840.113619.2.1.1.322.1600364094.412.3001" ) if result["success"]: print("Report text:", result["text_content"])

Fulcra Context MCP server for accessing your personal health, workouts, sleep, location, and more, all privately. Built around Context by Fulcra.

A healthcare MCP server for EMRs like Cerner and Epic, providing tools to interact with FHIR data and medical resources.

Read-only access to your Alma nutrition data, meals, goals, scores, workouts, weight history, pantry, and grocery list.

Bioinformatics data for AI agents — gene search, protein structures, clinical variants, PubMed literature, and DNA sequences via NCBI and UniProt. No API key required.

AI-powered cycling training coach: personalized training plans, daily workouts, nutrition, strength training, fitness metrics (FTP, VO2Max), and Strava, Garmin, Wahoo, MyWhoosh, and Rouvy integrations.

MCP Server para buscar médicos verificados en México. Busca doctores por especialidad, ciudad, estado. 5 tools de búsqueda.

FHIR MCP Server – helping you expose any FHIR Server or API as a MCP Server.

Local-first Garmin data warehouse: sync once into SQLite you own, then analyze trends, correlations, baselines and anomalies offline, even when Garmin's API breaks.

Healthcare FHIR R4 interoperability — patient records, care plans, clinical data exchange, HL7 compliance by MEOK AI Labs

A healthcare-focused RAG server using Groq API and Chroma for information retrieval from patient records.